Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mindspore-ai/akg --skill triton-ascend-case-reduction-prod-smallgit clone --depth 1 https://github.com/mindspore-ai/akgWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mindspore-ai/akg/triton-ascend-case-reduction-prod-small)<a href="https://agentmods.dev/skills/mindspore-ai/akg/triton-ascend-case-reduction-prod-small"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/triton-ascend-case-reduction-prod-small/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mindspore-ai/akg/triton-ascend-case-reduction-prod-small"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/triton-ascend-case-reduction-prod-small.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00095 | $0.00625 |
| Opus 5 | $0.00048 | $0.00313 |
| Sonnet 5 | $0.00019 | $0.00125 |
| Haiku 4.5 | $0.00010 | $0.00063 |
Grade A, and why
triton-ascend-case-reduction-prod-small scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
小规模 Prod 归约优化
任务特征
- 数据尺寸：(16, 2048)，reduce第一根轴，非reduce轴中等
优化：自定义reduce函数
# 简单
accumulator = tl.full((BLOCK_SIZE,), 1.0, dtype=tl.float32)
for m in range(M):
错误：accumulator = tl.where(mask, accumulator * data, accumulator)
# 正确：优化
@triton.jit
def mul(a, b):
return a * b
col_prod = tl.full((BLOCK_SIZE_M, BLOCK_SIZE_N), 1.0, dtype=tl.float32)
for m_start in range(0, M, BLOCK_SIZE_M):
col_prod *= block_vals
col_prod = tl.reduce(col_prod, axis=0, combine_fn=mul) # triton没有prod接口
Autotune 配置
# （AI core=40）
# 1. grid=64>40 -> 4.21 us
triton.Config({'BLOCK_SIZE_M': 16, 'BLOCK_SIZE_N': 32})
# 2. grid=40，有尾块 -> 3.28 us
triton.Config({'BLOCK_SIZE_M': 16, 'BLOCK_SIZE_N': 52})
# 3. grid=32<40 -> 2.61 us
triton.Config({'BLOCK_SIZE_M': 16, 'BLOCK_SIZE_N': 64})
# 4. grid=16<40 -> 2.15 us 最优
triton.Config({'BLOCK_SIZE_M': 16, 'BLOCK_SIZE_N': 128})
# 5. grid=2<40，UB占满 -> 2.63 us
triton.Config({'BLOCK_SIZE_M': 16, 'BLOCK_SIZE_N': 1024})
# 6. grid=1 -> 3.25 us
triton.Config({'BLOCK_SIZE_M': 8, 'BLOCK_SIZE_N': 2048})
总结
算子shape较小时（10^5~10^6元素），最优网格数可能需明显小于AI Core数量，过高并行度反而会因调度开销降低性能。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 61 lines · 95 tokens per session scan A 80a77ea5aeb0
triton-ascend-case-reduction-prod-small is a skill published in the GitHub repository mindspore-ai/akg (259 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 95 tokens to every session and 625 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
triton-ascend-case-reduction-weighted-swiglu
A performance-optimization method for a specialized 3D tensor operation using Weighted SwiGLU during backward computation. It reshapes data and divides work to improve parallel processing while keeping within on-chip memory limits.
triton-ascend-case-reduction-prod-small
A guide to optimizing small product reductions, which multiply a group of tensor values into one result.
triton-ascend-case-reduction-sum-large
A guide to optimizing large two-dimensional sum reductions when the non-reduced axis is very large and the reduced axis is medium-sized.
triton-ascend-case-elemwise-zeros
An optimization for creating small tensors with zeros, arange, or full in Triton Ascend. Triton Ascend is a programming environment for running tensor operations on Ascend hardware.
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.